发表机构
Universidad Autónoma de Madrid（马德里自治大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出模型无关的EPC分数，量化解释质量，经多模态实证及人类解释验证，可揭示网络激活等依赖关系，与人类判断高度一致。
AI 中文摘要
深度学习模型在高风险领域的快速普及，加剧了对可解释人工智能（XAI）可信赖性的需求。然而，客观评估解释保真度、使XAI指标与以人为中心的理解保持一致，仍是关键的开放挑战。本研究提出一种模型无关的指标——EPC分数，它是可解释性-性能系数（EPC）的扩展，通过明确平衡特征选择稀疏性与保留模型性能之间的权衡来量化解释质量。通过对表格、文本和图像模态的实证验证，我们发现EPC分数能有效揭示网络激活、数据维度与解释器性能之间的操作依赖关系。此外，我们针对独立的人类解释验证了EPC分数，证明更高的EPC分数与人类词汇情感判断、空间视觉标注高度一致。
英文摘要
The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI). However, objectively evaluating explanation fidelity and aligning XAI metrics with human-centered understanding remain critical open challenges. In this work, we propose a model-agnostic metric, the EPC score, which is an extension of the Explainability-Performance Coefficient (EPC), that quantifies explanation quality by explicitly balancing the trade-off between feature selection sparsity and preserved model performance. Through an empirical validation across tabular, text, and image modalities, we show that the EPC score effectively uncovers operational dependencies among network activations, data dimensionality, and explainer performance. Furthermore, we validate the EPC score against independent human-based explanations, proving that higher EPC scores strongly align with human lexical sentiment judgments and spatial visual annotations.
